@OwainEvans_UK 2024-07-08 ♥30 ↻4 original ↗
Yes, I was surprised by this result and I suspect few people would have predicted it in advance. It'd be good to understand how this ability scales.

(I'd already seen GPT-4-base spontaneously describe its own text as "generated by a language model" when it was sampled at temp<1. This is another orthogonal source of situational awareness -- which @repligate drew my attention to. But I hadn't seen it do this at temp=1, which is how we sampled for this task.)

We discuss this in the paper (page 109).

author:owainevans_uk kind:tweet model:gpt-4-base on:gpt-4-base year:2024

cited on: gpt-4-base

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.